worker_run_read_only

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Strong disclosure beyond the annotations: it says the call writes only the worker job record and command evidence, and that write/network/shell are forced disabled with workspace policy, timeout, env allowlist, redaction, and bounded output applied. That also resolves the apparent tension between the 'read_only' name and readOnlyHint=false. It stops short of saying what happens on policy violation or timeout (failure semantics).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and then the behavioral guarantees. The trailing clause chain ('applies workspace policy, timeout, env allowlist, redaction, and bounded output') is compressed but each element carries information, so there is little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Behavioral context is solid for a mutation-adjacent tool with no output schema, but completeness suffers on the input side: four required parameters (kind, workspace_root, cwd, argv) get no semantic explanation, and failure modes such as policy rejection or timeout are unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 13% (only authority_file is documented), so the description has to compensate. It adds meaning for argv (argv-only, no shell), timeout, and env_allowlist, but leaves kind, payload, cwd, and workspace_root unexplained, which is a real gap across 8 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Run an argv-only read-only command as a local worker evidence job.' That is concrete enough to separate it from a plain command runner, but it never names the nearest siblings (command_fake_run, worker_enqueue, command_policy_check), so the agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: it is for read-only commands executed as a local worker evidence job. There is no explicit when-to-use versus worker_enqueue, command_fake_run, or command_policy_check, and no statement of prerequisites or what to do when a command is not read-only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.